Introducing a novel multi-layer perceptron network based on stochastic gradient descent optimized by a meta-heuristic algorithm for landslide susceptibility mapping.

The main objective of the current study was to present a methodological approach that combines Information Theory, a neural network and meta-heuristic techniques so as to generate a landslide susceptibility map. Specifically, the methodology involved three important tasks: Classifying the landslide related variables, weighting them and optimizing the structural parameters of the neural network. Shannon's entropy index was used to estimate for each landslide related variable the number of classes which maximized the information coefficient, whereas the Certainty Factor method was used to weight the variables. A Neural Network, a (NN) which uses stochastic gradient descent (SGD), the structural parameters of which are optimized by a Genetic Algorithm (GA), was implemented to generate the landslide susceptibility map. A well defined spatial database which included 380 landslides and fourteen related variables (elevation, slope, aspect, plan curvature, profile curvature, topographic wetness index, stream power index, stream transport index, land use cover, distance to road, distance to faults, distance to river, lithology and soil cover) were considered for implementing the NN-SGD-GA model, in the Yanshan County located in Shangrao Municipality, in the north-eastern of Jiangxi province, China. To validate the predictive power of the novel model, a Logistic Regression (LR) and Random Forest (RF) model were used for comparison. The results showed that the NN-SGD-GA model achieved the highest prediction accuracy (88.10%), followed by the RF (86.26%) and the LR (85.82%) models. Furthermore, by analyzing the validation data, concerning the spatial distribution of landslides and the susceptibility index, the proposed model showed an area under curve value of 0.8212, followed by the RF (0.8124) and the LR (0.8020) models. Finally, the proposed model showed the highest relative landslide density value of 65.09, followed by the RF (62.51) and the LR (61.76) models, when using the validation dataset. The novelty of our approach is the usage of an intelligent way to select and classify the most appropriate prognostic variables and also the implementation of an evolutionary wrapper automatic procedure that efficiently generates prediction models with reduced complexity and adequate generalization capacity. Overall, the proposed model can be successfully used for landslide susceptibility mapping as an alternative spatial investigation tool.

Groundwater spring potential mapping using population-based evolutionary algorithms and data mining methods.

Water scarcity in many regions of the world has become an unpleasant reality. Groundwater appears to be one of the main natural resources capable to reverse this situation. Uncovering the spatial patterns of groundwater occurrence is a crucial factor that could assist in carrying out successful water resources management projects. The main objective of the current study was to provide a novel methodology approach which utilized Genetic Algorithm (GA) in order to perform a feature selection procedure and data mining methods for generating a groundwater spring potential map. Three data mining methods, Naïve Bayes (NB), Support Vector Machine (SVM) and Random Forest (RF) were utilized to construct a groundwater spring potential map that had over 0.81 probability of occurrence for the Wuqi County, Shaanxi Province, China. Groundwater spring locations and sixteen related variables were analyzed, namely: lithology, soil cover, land use cover, normalized difference vegetation index (NDVI), elevation, slope angle, aspect, planform curvature, profile curvature, curvature, stream power index (SPI), stream transport index (STI), topographic wetness index (TWI), mean annual rainfall, distance from river network and distance from road network. The Frequency ratio method was used to weight the variables, whereas a multi-collinearity analysis was performed to identify the relation between the parameters and to decide about their usage. The optimal set of parameters, which was determined by the GA, reduced the number of parameters into twelve removing planform curvature, profile curvature, curvature and STI. The Receiver Operating Characteristic curve and the area under the curve (AUROC) were estimated so as to evaluate the predictive power of each model. The results indicated that the optimized models were superior in accuracy than the original models. The optimized RF model produced the best results (0.9572), followed by the optimized SVM (0.9529) and the optimized NB (0.8235). Overall, the current study highlights the necessity of applying feature selection techniques in groundwater spring assessments and also that data mining methods may be a highly powerful investigation approach for groundwater spring potential mapping.

Land subsidence phenomena investigated by spatiotemporal analysis of groundwater resources, remote sensing techniques, and random forest method: the case of Western Thessaly, Greece.

The main objective of the present study was to investigate land subsidence phenomena and the spatiotemporal pattern of groundwater resources in an area located in western Thessaly, Greece, by using remote sensing techniques and data mining methods. Specifically, the nonparametric Mann-Kendall test and the Sen's slope estimator were used to estimate the trend concerning the groundwater table, whereas a set of Synthetic Aperture Radar images, processed with the Persistent Scatterer Interferometry technique, were used investigate the spatial and temporal patterns of ground deformation. Random forest (RF) method was utilized to predict the subsidence deformation rate based on three related variables, namely: thickness of loose deposits, the Sen's slope value of groundwater-level trend, and the Compression Index of the formation covering the area of interest. The outcomes of the study suggest a strong correlation among the thickness of the loose deposits and the deformation rate and also show that a clear trend between the deformation rate and the fluctuation of the groundwater table exists. For the RF model and based on the validation dataset, the r square value was calculated to be 0.7503. In the present study, the potential deformation rate assuming different water pumping scenarios was also estimated. It was observed that with a mean decrease in the Sen's slope value of groundwater-level trend of 20%, there would be a mean decrease of 9.01% in the deformation rate, while with a mean increase in the Sen's slope value of groundwater-level trend of 20%, there would be a mean increase of 12.12% in the deformation rate. The ability of identifying surface deformations allows the local authorities and government agencies to take measures before the evolution of severe subsidence phenomena and to prepare for timely protection of the affected areas.

Applying genetic algorithms to set the optimal combination of forest fire related variables and model forest fire susceptibility based on data mining models. The case of Dayu County, China.

The main objective of the present study was to utilize Genetic Algorithms (GA) in order to obtain the optimal combination of forest fire related variables and apply data mining methods for constructing a forest fire susceptibility map. In the proposed approach, a Random Forest (RF) and a Support Vector Machine (SVM) was used to produce a forest fire susceptibility map for the Dayu County which is located in southwest of Jiangxi Province, China. For this purpose, historic forest fires and thirteen forest fire related variables were analyzed, namely: elevation, slope angle, aspect, curvature, land use, soil cover, heat load index, normalized difference vegetation index, mean annual temperature, mean annual wind speed, mean annual rainfall, distance to river network and distance to road network. The Natural Break and the Certainty Factor method were used to classify and weight the thirteen variables, while a multicollinearity analysis was performed to determine the correlation among the variables and decide about their usability. The optimal set of variables, determined by the GA limited the number of variables into eight excluding from the analysis, aspect, land use, heat load index, distance to river network and mean annual rainfall. The performance of the forest fire models was evaluated by using the area under the Receiver Operating Characteristic curve (ROC-AUC) based on the validation dataset. Overall, the RF models gave higher AUC values. Also the results showed that the proposed optimized models outperform the original models. Specifically, the optimized RF model gave the best results (0.8495), followed by the original RF (0.8169), while the optimized SVM gave lower values (0.7456) than the RF, however higher than the original SVM (0.7148) model. The study highlights the significance of feature selection techniques in forest fire susceptibility, whereas data mining methods could be considered as a valid approach for forest fire susceptibility modeling.

Application of fuzzy weight of evidence and data mining techniques in construction of flood susceptibility map of Poyang County, China.

In China, floods are considered as the most frequent natural disaster responsible for severe economic losses and serious damages recorded in agriculture and urban infrastructure. Based on the international experience prevention of flood events may not be completely possible, however identifying susceptible and vulnerable areas through prediction models is considered as a more visible task with flood susceptibility mapping being an essential tool for flood mitigation strategies and disaster preparedness. In this context, the present study proposes a novel approach to construct a flood susceptibility map in the Poyang County, JiangXi Province, China by implementing fuzzy weight of evidence (fuzzy-WofE) and data mining methods. The novelty of the presented approach is the usage of fuzzy-WofE that had a twofold purpose. Firstly, to create an initial flood susceptibility map in order to identify non-flood areas and secondly to weight the importance of flood related variables which influence flooding. Logistic Regression (LR), Random Forest (RF) and Support Vector Machines (SVM) were implemented considering eleven flood related variables, namely: lithology, soil cover, elevation, slope angle, aspect, topographic wetness index, stream power index, sediment transport index, plan curvature, profile curvature and distance from river network. The efficiency of this new approach was evaluated using area under curve (AUC) which measured the prediction and success rates. According to the outcomes of the performed analysis, the fuzzy WofE-SVM model was the model with the highest predictive performance (AUC value, 0.9865) which also appeared to be statistical significant different from the other predictive models, fuzzy WofE-RF (AUC value, 0.9756) and fuzzy WofE-LR (AUC value, 0.9652). The proposed methodology and the produced flood susceptibility map could assist researchers and local governments in flood mitigation strategies.